Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/suyoumo/clawprobench/tech-debt-trackernpx skills add suyoumo/ClawProBench --skill tech-debt-trackergit clone --depth 1 https://github.com/suyoumo/ClawProBenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/suyoumo/clawprobench/tech-debt-tracker)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/tech-debt-tracker"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/tech-debt-tracker.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00032 | $0.01116 |
| Opus 5 | $0.00016 | $0.00558 |
| Sonnet 5 | $0.00006 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
tech-debt-tracker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Debt Tracker
Track technical debt from conversation and PR review comments. Debt items live in projects/commitments/tech-debt/ and are resurfaced weekly.
Mode A: Passive detection
When the user says something implying tech debt ("this is a hack but it works", "we should really refactor the auth module", "adding another TODO"), silently extract it.
Action:
- Check for duplicates via
memory_searchinprojects/commitments/tech-debt/. - Write to
projects/commitments/tech-debt/<slug>.md:
---
type: tech-debt
detected_at: <today YYYY-MM-DD>
repo: <current repo context if known, else null>
severity: <high|medium|low>
category: <refactor|performance|security|testing|documentation|architecture>
source: conversation
source_pr: null
---
# <Brief title>
<What the debt is and why it exists.>
## Context
<What prompted the shortcut — deadline, complexity, missing knowledge.>
## Proposed fix
<What a proper fix would look like, if discussed.>
Severity rules:
high: security shortcuts, data integrity risks, architectural violationsmedium: code quality, missing tests, poor abstractionslow: style issues, minor workarounds, documentation gaps
- At a natural pause: "Tracked tech debt: ."
Do NOT interrupt conversation flow.
Mode B: PR review scan (used by triage mission)
When the triage mission processes recently merged PRs, it should scan review comments for tech-debt patterns:
- "can be addressed in follow-up work"
- "not blocking but should fix later"
- "TODO: address in next PR"
- "leaving for now", "good enough for now"
- "nit: ... (not blocking)"
- "tech debt", "hack", "workaround" in review comments
For each match, create a tech-debt item with source: pr-review and source_pr: owner/repo#123.
Mode C: Explicit capture
User says: "add tech debt: the caching layer needs TTL eviction."
Write directly to projects/commitments/tech-debt/, confirm briefly.
Mode D: Listing
User says: "show tech debt" or "debt backlog"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 135 lines · 32 tokens per session scan A c2c1cc391d2a
tech-debt-tracker is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 9d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,116 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
langwatch-kanban
Manage the LangWatch Kanban GitHub project board — sync statuses, view your board, find stale items, move issues, assign work.
agenthub-models
Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.
benchmark-design
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.